41 of 51 criteria have a sourced finding; 38 were also cross-checked by a second agent. Every comparison that includes QM from YC links here for scope, limitations, atomic answers and sources.
Humans approve the rubric, templates and prototype; they do not review every finding. An agent source cross-check is not a hands-on product test. A missing sourced finding is not evidence that a capability is absent.
QM offers web/PWA, Slack and a published Apple Silicon Mac desktop client. Windows/Linux prototype source packaging is separate from published downloads; phone access uses the browser build.
Scope
Surfaces: QM web workspace, QM Slack plugin, QM core and deployment CLI, QM Desktop Apple Silicon · Version: First-party sources checked 2026-11-07; pinned implementations retain their cited revision. · Plan: Not specified · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
generally-available
Delivery
native
Checked
2026-11-07 (15 days old)
Agent cross-check
Not separately cross-checked
Documentation and pinned source inspection only; no hands-on scenario was run.
Other atomic questions remain unestablished: editor_extensions, notifications.
9 atomic answers
Desktop os [supported] QM Desktop 0.1.6 is offered for Apple Silicon Macs as a signed/notarized GitHub pre-release. Sources: qm:nov07-release.
Mobile apps [unsupported] The inspected public client inventory has no native iOS or Android app; its phone interface is the web/PWA build. Sources: qm:gaps-client-inventory.
Mobile browser [supported] Phone layout below 860px includes composer, approvals, drawers and home-screen PWA install. Sources: qm:gap-web.
Cli [partial] The qm CLI initializes, validates and deploys deployments; task-operation (chat) commands were not established. Sources: qm:nov07-readme.
Editor extensions [unknown] Editor extensions: The November first-party documentation and repository pass did not establish client access at the rubric's required scope. No installed-product fixture was run.
Task actions [supported] Phone web UI exposes composer/send, session menus, model/effort settings and approvals; no device handoff fixture. Sources: qm:gap-web.
Notifications [unknown] Notifications: The November first-party documentation and repository pass did not establish client access at the rubric's required scope. No installed-product fixture was run.
Cross device continuity [partial] Phones get the same web build with a phone layout; continuing a specific task across devices is not described and no handoff test was run. Sources: qm:gap-web.
The current QM core runs the Pi coding-agent loop. Model/provider subscription choices do not select a Claude Code, Codex or other coding-agent CLI harness. Each turn runs Pi inside the QM core; v0.1.16 removed harness choice, so one deployment cannot mix agent harnesses.
Scope
Surfaces: QM web workspace, QM Slack plugin, QM core and deployment CLI, QM Desktop Apple Silicon · Version: First-party sources checked 2026-11-07; pinned implementations retain their cited revision.; v0.1.18 (9c20219, 2026-11-11) for backfilled atoms · Plan: Not specified · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
generally-available
Delivery
native
Checked
2026-11-07 (15 days old)
Agent cross-check
2026-11-22
Documentation and pinned source inspection only; no hands-on scenario was run.
Other atomic questions remain unestablished: custom_adapters.
5 atomic answers
Harnesses [supported] The active core uses the Pi coding-agent library and supplies no selectable adapter for the other named coding-agent CLIs. Sources: qm:gaps-pi-loop.
Model providers [supported] Selectable models through Pi from multiple providers. Sources: qm:nov07-readme.
Custom adapters [unknown] Custom adapters: The November first-party documentation and repository pass did not establish agent and model choice at the rubric's required scope. No installed-product fixture was run.
Session integration [supported] Embedded: the Pi agent loop runs inside the QM core for every turn; QM owns sessions, tools and sandboxes. Sources: qm:b06-readme.
Mixed harness operation [unsupported] v0.1.16 kept one harness and a v0.1.18 migration strips harnessId from every runtime, cron, subagent and swarm config, so harnesses cannot be mixed. Sources: qm:b06-rel-0116, qm:b06-harness-migration.
QM supports both operator-provided model keys and personal Claude or ChatGPT/Codex subscription sign-in for human turns. Background work uses company access.
Scope
Surfaces: QM web workspace, QM Slack plugin, QM core and deployment CLI, QM Desktop Apple Silicon · Version: First-party sources checked 2026-11-07; pinned implementations retain their cited revision. · Plan: Not specified · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
generally-available
Delivery
native
Checked
2026-11-07 (15 days old)
Agent cross-check
Not separately cross-checked
Documentation and pinned source inspection only; no hands-on scenario was run.
Other atomic questions remain unestablished: vendor_credits, local_models, account_switching, provider_restrictions.
7 atomic answers
Agent subscriptions [supported] The Personal AI accounts guide documents subscription sign-in for Claude and ChatGPT/Codex, backed by native provider OAuth and refresh paths. Sources: qm:gaps-personal-accounts.
Api accounts [supported] Own models and keys. Sources: qm:nov07-readme.
Vendor credits [unknown] Vendor credits: The November first-party documentation and repository pass did not establish subscriptions, api keys and vendor credits at the rubric's required scope. No installed-product fixture was run.
Local models [unknown] Local models: The November first-party documentation and repository pass did not establish subscriptions, api keys and vendor credits at the rubric's required scope. No installed-product fixture was run.
Account switching [unknown] Account switching: The November first-party documentation and repository pass did not establish subscriptions, api keys and vendor credits at the rubric's required scope. No installed-product fixture was run.
Vendor account requirement [partial] Deploy in the operator cloud account; third-party hosted QM is separate. Sources: qm:nov07-readme.
Provider restrictions [unknown] Provider restrictions: The November first-party documentation and repository pass did not establish subscriptions, api keys and vendor credits at the rubric's required scope. No installed-product fixture was run.
QM supplies an agent-guided deployment directory and requires Postgres. No YC-run hosted service: one-click templates on DigitalOcean, E2B and Render and a third-party hosted option (Agent 37).
Scope
Surfaces: QM web workspace, QM Slack plugin, QM core and deployment CLI, QM Desktop Apple Silicon · Version: First-party sources checked 2026-11-07; pinned implementations retain their cited revision.; v0.1.18 (9c20219, 2026-11-11) for backfilled atoms · Plan: Not specified · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
generally-available
Delivery
native
Checked
2026-11-07 (15 days old)
Agent cross-check
2026-11-22
The remaining atomic questions and the rubric scenario are unverified. Documentation is not a successful product test.
7 atomic answers
First task setup [partial] Guided deployment and verification, not an observed successful install. Sources: qm:nov07-readme.
No git [unknown] No git: The November first-party documentation and repository pass did not establish onboarding and project prerequisites at the rubric's required scope. No installed-product fixture was run.
Local git without remote [unknown] Local git without remote: The November first-party documentation and repository pass did not establish onboarding and project prerequisites at the rubric's required scope. No installed-product fixture was run.
Hosted git [unknown] Hosted git: The November first-party documentation and repository pass did not establish onboarding and project prerequisites at the rubric's required scope. No installed-product fixture was run.
Prerequisite guidance [supported] Node and Postgres plus cloud, sign-in and connector credentials. Sources: qm:nov07-readme.
Managed cloud setup [partial] No YC-run managed service. DigitalOcean, E2B and Render offer one-click templates and Agent 37 a third-party fully hosted option; YC only collects interest in a hosted version. Sources: qm:b06-readme.
Byo vps onboarding [partial] qm init targets Fly or AWS and materializes an installation skill; setup effort unmeasured. Sources: qm:nov07-readme.
Core HTTP APIs and scoped swarm routes provide programmatic operations. The qm CLI handles deployment and operations only; inbound webhooks wake agent turns.
Scope
Surfaces: QM web workspace, QM Slack plugin, QM core and deployment CLI, QM Desktop Apple Silicon · Version: First-party sources checked 2026-11-07; pinned implementations retain their cited revision.; v0.1.18 (9c20219, 2026-11-11) for backfilled atoms · Plan: Not specified · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
generally-available
Delivery
native
Checked
2026-11-07 (15 days old)
Agent cross-check
2026-11-22
The remaining atomic questions and the rubric scenario are unverified. Documentation is not a successful product test.
8 atomic answers
Cli [partial] qm is a deployment and operations CLI (init, up, logs, secrets, ui publish and similar); starting or steering agent work goes through the HTTP API, Slack or the web UI. Sources: qm:b06-cli, qm:b06-readme.
Sdk [unknown] Sdk: The November first-party documentation and repository pass did not establish programmable access at the rubric's required scope. No installed-product fixture was run.
Mcp server [unknown] Mcp server: The November first-party documentation and repository pass did not establish programmable access at the rubric's required scope. No installed-product fixture was run.
Webhooks [supported] Inbound webhooks: POST /v1/webhooks creates one and /v1/webhooks/incoming/:id delivers verified events that wake background work. Sources: qm:b06-webhooks, qm:b06-readme.
Stability [unknown] Stability: The November first-party documentation and repository pass did not establish programmable access at the rubric's required scope. No installed-product fixture was run.
QM provides administrator-registered HTTP MCP connectors and own-deployment customization. Deployments add custom tools and skills under sandbox/, services under plugins/, and admins import skill packs from git.
Scope
Surfaces: QM core and deployment CLI, QM web workspace · Version: First-party documentation/source checked 2026-11-07; exact pinned source revision is recorded in each citation. No installed-product fixture.; v0.1.18 (9c20219, 2026-11-11) for backfilled atoms · Plan: Not specified · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
unknown
Delivery
unknown
Checked
2026-11-07 (15 days old)
Agent cross-check
2026-11-22
Only the named atomic facts are established by documentation. Remaining rubric scenarios and unknown answers were not demonstrated.
Plugins [supported] Admins import skill packs from git repositories at pinned refs into chosen scopes; deployments add services under plugins/ and skills under sandbox/skills/. Sources: qm:b06-skill-registry, qm:b06-deploy-dir.
Custom tools [supported] Deployment directories add custom tools as sandbox/tools/<id>/tool.json plus binaries, synced to core as a versioned deployment layer. Sources: qm:b06-deploy-dir.
Instructions import [unknown] Instructions import: The November first-party documentation and repository pass did not establish external tools and extensions at the rubric's required scope. No installed-product fixture was run.
Authentication [supported] Shared/client credentials or per-user OAuth/PKCE with persistent encrypted connector keychain. Sources: qm:gap-mcp.
Permission scope [supported] Administrator chooses destination/tools and approval policy; per-user calls use initiating actor credentials. Sources: qm:gap-mcp.
The web package uses Lit with Vite. Desktop is an Electron shell running the same web UI; iOS is a native SwiftUI client.
Scope
Surfaces: QM web workspace · Version: First-party sources checked 2026-11-07; pinned implementations retain their cited revision.; v0.1.18 (9c20219, 2026-11-11) for backfilled atoms · Plan: Not specified · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
generally-available
Delivery
native
Checked
2026-11-07 (15 days old)
Agent cross-check
2026-11-22
Documentation and source inspection of v0.1.18 only; no installed client was run. The macOS desktop build is an unsigned local prototype and iOS is built from source.
4 atomic answers
Desktop implementation [supported] Electron client that runs the same web UI against an existing deployment; the macOS build is an unsigned local prototype. Sources: qm:b06-desktop.
Mobile implementation [supported] Native SwiftUI iOS 18+ client with no embedded WebKit product UI, using the authenticated APIs; built from source. Sources: qm:b06-ios.
QM accepts human prompts in personal and shared channels.
Scope
Surfaces: QM web workspace, QM Slack plugin, QM core and deployment CLI, QM Desktop Apple Silicon · Version: First-party sources checked 2026-11-07; pinned implementations retain their cited revision. · Plan: Not specified · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
generally-available
Delivery
native
Checked
2026-11-07 (15 days old)
Agent cross-check
2026-11-07
The remaining atomic questions and the rubric scenario are unverified. Documentation is not a successful product test.
9 atomic answers
Local creation [unknown] Local creation: The November first-party documentation and repository pass did not establish intake and external tracker relationship at the rubric's required scope. No installed-product fixture was run.
Prompt intake [supported] Personal chat and shared Slack/web rooms. Sources: qm:nov07-readme.
External import [unknown] External import: The November first-party documentation and repository pass did not establish intake and external tracker relationship at the rubric's required scope. No installed-product fixture was run.
Chat git triggers [unknown] Chat git triggers: The November first-party documentation and repository pass did not establish intake and external tracker relationship at the rubric's required scope. No installed-product fixture was run.
Authoritative tracker [unknown] The checked first-party sources did not establish authoritative tracker at this criterion's scope; no installed fixture was run.
Stable ids [unknown] Stable ids: The November first-party documentation and repository pass did not establish intake and external tracker relationship at the rubric's required scope. No installed-product fixture was run.
Sync [unknown] Sync: The November first-party documentation and repository pass did not establish intake and external tracker relationship at the rubric's required scope. No installed-product fixture was run.
Supported edits [unknown] Supported edits: The November first-party documentation and repository pass did not establish intake and external tracker relationship at the rubric's required scope. No installed-product fixture was run.
External roundtrips [unknown] External roundtrips: The November first-party documentation and repository pass did not establish intake and external tracker relationship at the rubric's required scope. No installed-product fixture was run.
QM memory uses scoped revisioned records and grant-based skills.
Scope
Surfaces: QM web workspace, QM Slack plugin, QM core and deployment CLI, QM Desktop Apple Silicon · Version: First-party sources checked 2026-11-07; pinned implementations retain their cited revision. · Plan: Not specified · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
generally-available
Delivery
native
Checked
2026-11-07 (15 days old)
Agent cross-check
2026-11-07
The remaining atomic questions and the rubric scenario are unverified. Documentation is not a successful product test.
Only the named atomic facts are established by documentation. Remaining rubric scenarios and unknown answers were not demonstrated.
10 atomic answers
Instructions [unknown] Instructions: The November first-party documentation and repository pass did not establish shared context and memory at the rubric's required scope. No installed-product fixture was run.
Skills [supported] Scope-owned skills with sharing grants and admin promotion. Sources: qm:nov07-readme.
Memory [supported] Personal and room memory. Sources: qm:nov07-readme.
Scope [supported] Per-person and per-room scopes. Sources: qm:nov07-readme.
Provenance [supported] Records retain stable ID, sensitivity and source scope/session; missing provenance remains unknown. Sources: qm:gap-memory.
Correction [supported] Structured edits and consolidation use revision checks; concurrent edits beat stale consolidation. Sources: qm:gap-memory.
Deletion [supported] Clearing removes current memory content, not historical revisions. Sources: qm:gap-memory.
Freshness [supported] Read authorization rechecks source access on each read; stale authorization is not cached. Sources: qm:gap-memory.
Takeover continuity [unknown] Takeover continuity: The November first-party documentation and repository pass did not establish shared context and memory at the rubric's required scope. No installed-product fixture was run.
QM can search notes, documents, email, databases and web; scoped memory retrieval does not prove architecture enforcement.
Scope
Surfaces: QM core and deployment CLI, QM web workspace · Version: First-party documentation/source checked 2026-11-07; exact pinned source revision is recorded in each citation. No installed-product fixture. · Plan: Not specified · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
unknown
Delivery
unknown
Checked
2026-11-07 (15 days old)
Agent cross-check
2026-11-07
Only the named atomic facts are established by documentation. Remaining rubric scenarios and unknown answers were not demonstrated.
10 atomic answers
Code search [unknown] Code search: The November first-party documentation and repository pass did not establish architecture and api awareness at the rubric's required scope. No installed-product fixture was run.
Indexing [unknown] Indexing: The November first-party documentation and repository pass did not establish architecture and api awareness at the rubric's required scope. No installed-product fixture was run.
External knowledge [supported] README documents searching internal notes, email, documents, databases and web together. Sources: qm:nov07-readme.
Multimodal inputs [unknown] Multimodal inputs: The November first-party documentation and repository pass did not establish architecture and api awareness at the rubric's required scope. No installed-product fixture was run.
Freshness [unknown] Freshness: The November first-party documentation and repository pass did not establish architecture and api awareness at the rubric's required scope. No installed-product fixture was run.
Access scope [unknown] Access scope: The November first-party documentation and repository pass did not establish architecture and api awareness at the rubric's required scope. No installed-product fixture was run.
Api retrieval [unknown] Api retrieval: The November first-party documentation and repository pass did not establish architecture and api awareness at the rubric's required scope. No installed-product fixture was run.
Citations [unknown] Citations: The November first-party documentation and repository pass did not establish architecture and api awareness at the rubric's required scope. No installed-product fixture was run.
Conflict detection [unknown] Conflict detection: The November first-party documentation and repository pass did not establish architecture and api awareness at the rubric's required scope. No installed-product fixture was run.
Review enforcement [unknown] Review enforcement: The November first-party documentation and repository pass did not establish architecture and api awareness at the rubric's required scope. No installed-product fixture was run.
The current QM API and web UI expose conversations/runs, schedules and approvals without a native independent issue tracker. The run task list was removed in October 2026; preview Loop items carry status and triage priority.
Scope
Surfaces: QM web workspace, QM Slack plugin, QM core and deployment CLI, QM Desktop Apple Silicon · Version: v0.1.18 (9c20219, 2026-11-11) for backfilled atoms · Plan: Not specified · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
generally-available
Delivery
native
Checked
2026-11-13 (9 days old)
Agent cross-check
2026-11-22
Documentation and pinned source inspection only; no hands-on scenario was run.
The create and durable_states answers rest on a bounded inspection at 1c61ee3, before preview Loops. At v0.1.18, Loop ledger items behind the inbox_loops flag (default off, enabled per personal scope by an admin) can be upserted, edited, dismissed and reopened through /v1/loops/:id/items; whether they serve as a general native issue tracker is not established.
17 atomic answers
Create [unsupported] No issue/task CRUD route or independent native issue record is exposed in the current core and UI. Sources: qm:gaps-public-model.
Edit [unknown] Edit: The November first-party documentation and repository pass did not establish native issue management and idea backlog at the rubric's required scope. No installed-product fixture was run.
Discuss [unknown] Discuss: The November first-party documentation and repository pass did not establish native issue management and idea backlog at the rubric's required scope. No installed-product fixture was run.
Prioritize [unknown] Prioritize: The November first-party documentation and repository pass did not establish native issue management and idea backlog at the rubric's required scope. No installed-product fixture was run.
Label [unknown] Label: The November first-party documentation and repository pass did not establish native issue management and idea backlog at the rubric's required scope. No installed-product fixture was run.
Assign [unknown] Assign: The November first-party documentation and repository pass did not establish native issue management and idea backlog at the rubric's required scope. No installed-product fixture was run.
Search [unknown] Search: The November first-party documentation and repository pass did not establish native issue management and idea backlog at the rubric's required scope. No installed-product fixture was run.
Filter [unknown] Filter: The November first-party documentation and repository pass did not establish native issue management and idea backlog at the rubric's required scope. No installed-product fixture was run.
Archive [unknown] Archive: The November first-party documentation and repository pass did not establish native issue management and idea backlog at the rubric's required scope. No installed-product fixture was run.
Reopen [unknown] Reopen: The November first-party documentation and repository pass did not establish native issue management and idea backlog at the rubric's required scope. No installed-product fixture was run.
Project epic views [unknown] Project epic views: The November first-party documentation and repository pass did not establish native issue management and idea backlog at the rubric's required scope. No installed-product fixture was run.
Idea parking [unknown] Idea parking: The November first-party documentation and repository pass did not establish native issue management and idea backlog at the rubric's required scope. No installed-product fixture was run.
Explicit dispatch [unknown] Explicit dispatch: The November first-party documentation and repository pass did not establish native issue management and idea backlog at the rubric's required scope. No installed-product fixture was run.
Task session separation [unknown] Task session separation: The November first-party documentation and repository pass did not establish native issue management and idea backlog at the rubric's required scope. No installed-product fixture was run.
Metadata [partial] No general task or issue records: the run task list (title, session, origin run, state) was removed on 2026-10-14. Preview Inbox/Loop items, off by default, carry status and urgent-to-low triage priority; no labels or backlog fields. Sources: qm:b06-task-removal, qm:b06-loops.
Durable states [unsupported] Durable states in the accessible product belong to runs, sessions or scheduled work rather than independent native issues. Sources: qm:gaps-public-model.
External tracker requirement [unknown] External tracker requirement: The November first-party documentation and repository pass did not establish native issue management and idea backlog at the rubric's required scope. No installed-product fixture was run.
Surfaces: QM web workspace, QM Slack plugin, QM core and deployment CLI, QM Desktop Apple Silicon · Version: First-party sources checked 2026-11-07; pinned implementations retain their cited revision. · Plan: Not specified · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
unknown
Delivery
native
Checked
2026-11-07 (15 days old)
Agent cross-check
2026-11-07
Swarms is off by default and requires a per-person or organization feature flag. No live worker fixture was run.
The swarms document gates this behind a feature flag and states no release stage.
5 atomic answers
Concurrent sessions [supported] Worker sessions with separate durable transcripts. Sources: qm:nov07-swarms.
Concurrent tasks [unknown] Concurrent tasks: The November first-party documentation and repository pass did not establish parallel work at the rubric's required scope. No installed-product fixture was run.
Quotas [supported] Default lifetime agent budget includes root and failed reservations. Sources: qm:nov07-swarms.
Observed concurrency [unknown] Observed concurrency: The November first-party documentation and repository pass did not establish parallel work at the rubric's required scope. No installed-product fixture was run.
Status visibility [supported] Inspect reports active, starting, paused, stopped and failed workers. Sources: qm:nov07-swarms.
Swarms dispatch durable reserved workers and deduplicate retried spawn/send requests by requestId.
Scope
Surfaces: QM core and deployment CLI, QM web workspace · Version: First-party documentation/source checked 2026-11-07; exact pinned source revision is recorded in each citation. No installed-product fixture. · Plan: Not specified · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
unknown
Delivery
unknown
Checked
2026-11-07 (15 days old)
Agent cross-check
2026-11-10
Only the named atomic facts are established by documentation. Remaining rubric scenarios and unknown answers were not demonstrated.
The swarms document gates this behind a feature flag and states no release stage.
7 atomic answers
Human assignment [unknown] Human assignment: The November first-party documentation and repository pass did not establish ownership and dispatch at the rubric's required scope. No installed-product fixture was run.
Agent assignment [unknown] Agent assignment: The November first-party documentation and repository pass did not establish ownership and dispatch at the rubric's required scope. No installed-product fixture was run.
Claims [unknown] Claims: The November first-party documentation and repository pass did not establish ownership and dispatch at the rubric's required scope. No installed-product fixture was run.
Queues [supported] Outbox queues initial turns and notifications after worker provisioning. Sources: qm:gap-swarms.
Routing [unknown] Routing: The November first-party documentation and repository pass did not establish ownership and dispatch at the rubric's required scope. No installed-product fixture was run.
Duplicate prevention [supported] Same requestId and identical payload return original reservation/message; changed payload fails. Sources: qm:gap-swarms.
Ownership enforcement [supported] Agent controls only itself/descendants; authorized human controls workers in swarm scope. Sources: qm:gap-swarms.
Results return [supported] Normal session viewer/run APIs. Sources: qm:nov07-swarms.
Cross harness [unknown] Cross harness: The November first-party documentation and repository pass did not establish inspectable delegation and communication at the rubric's required scope. No installed-product fixture was run.
Live progress [unknown] Live progress: The November first-party documentation and repository pass did not establish inspectable delegation and communication at the rubric's required scope. No installed-product fixture was run.
Retained results [supported] Worker transcripts and results remain visible through durable session viewer APIs. Sources: qm:gap-swarms.
Followup [partial] Worker web transcripts are read-only for normal human messages; pending approvals can be answered. Sources: qm:nov07-swarms.
Invocation [supported] Root or workers call spawn with count/context/model settings; workers recursively spawn under depth budget. Sources: qm:gap-swarms.
Events [supported] Watches and inbound webhooks. Sources: qm:nov07-readme.
Recurring tasks [supported] Crons (cron expression with timezone, fixed interval or first-fire time) are fired by the core scheduler on the deployment. Sources: qm:b06-crons, qm:b06-readme.
Completion conditions [unknown] Completion conditions: The November first-party documentation and repository pass did not establish unattended triggers at the rubric's required scope. No installed-product fixture was run.
Overlaps [unknown] Overlaps: The November first-party documentation and repository pass did not establish unattended triggers at the rubric's required scope. No installed-product fixture was run.
Retries [unknown] Retries: The November first-party documentation and repository pass did not establish unattended triggers at the rubric's required scope. No installed-product fixture was run.
Client independence [supported] README explicitly describes background work while away, owned by headless deployed core. Sources: qm:nov07-readme.
Notifications [unknown] Notifications: The November first-party documentation and repository pass did not establish intervention and attention at the rubric's required scope. No installed-product fixture was run.
Pending decisions [supported] Requesting human can allow/deny pending worker approvals through read-only worker transcript. Sources: qm:gap-swarms.
Escalation [unknown] Escalation: The November first-party documentation and repository pass did not establish intervention and attention at the rubric's required scope. No installed-product fixture was run.
Visible errors [supported] Failed provisioning and worker states appear in inspect. Sources: qm:nov07-swarms.
Chat terminal parity [unknown] Chat terminal parity: The November first-party documentation and repository pass did not establish intervention and attention at the rubric's required scope. No installed-product fixture was run.
Web swarm strip groups workers under parents and exposes control/status. Fleet fixture remains untested.
Scope
Surfaces: QM core and deployment CLI, QM web workspace · Version: First-party documentation/source checked 2026-11-07; exact pinned source revision is recorded in each citation. No installed-product fixture. · Plan: Not specified · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
unknown
Delivery
unknown
Checked
2026-11-07 (15 days old)
Agent cross-check
2026-11-10
Only the named atomic facts are established by documentation. Remaining rubric scenarios and unknown answers were not demonstrated.
The swarms document gates this behind a feature flag and states no release stage.
The swarms document says the agent-board UI is intentionally deferred; only the Swarm strip on swarm sessions is described.
8 atomic answers
Fleet fixture [unknown] Fleet fixture: The November first-party documentation and repository pass did not establish fleet and epic management ui at the rubric's required scope. No installed-product fixture was run.
Parent child [supported] Expanded strip groups workers by parent, twenty per group with show-more. Sources: qm:gap-swarms.
Dependencies [unknown] Dependencies: The November first-party documentation and repository pass did not establish fleet and epic management ui at the rubric's required scope. No installed-product fixture was run.
History [supported] Worker session URLs link retained transcripts/results. Sources: qm:gap-swarms.
Workload [partial] Strip summary counts workers by state and offers per-worker and cascading Pause/Resume/Stop all; per-agent workload views are not described. Sources: qm:gap-swarms.
Navigation errors [unknown] Navigation errors: The November first-party documentation and repository pass did not establish fleet and epic management ui at the rubric's required scope. No installed-product fixture was run.
Fixture mode [unknown] Fixture mode: The November first-party documentation and repository pass did not establish fleet and epic management ui at the rubric's required scope. No installed-product fixture was run.
Feature-flagged swarm workers expose configuration and retained session identities.
Scope
Surfaces: QM web workspace, QM Slack plugin, QM core and deployment CLI, QM Desktop Apple Silicon · Version: First-party sources checked 2026-11-07; pinned implementations retain their cited revision. · Plan: Not specified · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
unknown
Delivery
native
Checked
2026-11-07 (15 days old)
Agent cross-check
2026-11-07
The remaining atomic questions and the rubric scenario are unverified. Documentation is not a successful product test.
The swarms document gates this behind a feature flag and states no release stage.
10 atomic answers
Quick task [unknown] Quick task: The November first-party documentation and repository pass did not establish workflow flexibility and orchestration visibility at the rubric's required scope. No installed-product fixture was run.
Growing epic [unknown] Growing epic: The November first-party documentation and repository pass did not establish workflow flexibility and orchestration visibility at the rubric's required scope. No installed-product fixture was run.
Presets [unknown] Presets: The November first-party documentation and repository pass did not establish workflow flexibility and orchestration visibility at the rubric's required scope. No installed-product fixture was run.
Natural language [unknown] Natural language: The November first-party documentation and repository pass did not establish workflow flexibility and orchestration visibility at the rubric's required scope. No installed-product fixture was run.
In run changes [unknown] In run changes: The November first-party documentation and repository pass did not establish workflow flexibility and orchestration visibility at the rubric's required scope. No installed-product fixture was run.
Live roles [unknown] Live roles: The November first-party documentation and repository pass did not establish workflow flexibility and orchestration visibility at the rubric's required scope. No installed-product fixture was run.
Discoverability [unknown] Discoverability: The November first-party documentation and repository pass did not establish workflow flexibility and orchestration visibility at the rubric's required scope. No installed-product fixture was run.
QM runs its headless core and agent resources on operator infrastructure. In addition to operator-cloud deployments, a local Docker sandbox provider runs tools on an operator computer; cloud-owned core work is independent of browser clients.
Scope
Surfaces: QM web workspace, QM Slack plugin, QM core and deployment CLI, QM Desktop Apple Silicon · Version: First-party sources checked 2026-11-07; pinned implementations retain their cited revision.; v0.1.18 (9c20219, 2026-11-11) for backfilled atoms · Plan: Not specified · OS: Not specified · Execution modes: operator-owned-cloud · Region: Not specified · Harness: Not specified
Availability
generally-available
Delivery
native
Checked
2026-11-07 (15 days old)
Agent cross-check
2026-11-22
Documentation and pinned source inspection only; no hands-on scenario was run.
Other atomic questions remain unestablished: hybrid, resources, region, expiry, other_device_continuation.
12 atomic answers
Local [supported] The local Docker sandbox provider and build path execute agent tools on the operator host. Sources: qm:gaps-local-docker.
Byo remote [supported] Each deployment runs in operator cloud account with headless core. Sources: qm:nov07-readme.
Managed cloud [partial] No YC-run managed cloud; Agent 37 offers a third-party fully hosted version and DigitalOcean, E2B and Render offer templates in the operator's account. Sources: qm:b06-readme.
Hybrid [unknown] Hybrid: The November first-party documentation and repository pass did not establish laptop-independent execution at the rubric's required scope. No installed-product fixture was run.
Resources [unknown] Resources: The November first-party documentation and repository pass did not establish laptop-independent execution at the rubric's required scope. No installed-product fixture was run.
Region [unknown] Region: The November first-party documentation and repository pass did not establish laptop-independent execution at the rubric's required scope. No installed-product fixture was run.
Expiry [unknown] Expiry: The November first-party documentation and repository pass did not establish laptop-independent execution at the rubric's required scope. No installed-product fixture was run.
Client disconnect [supported] Background crons/watches/webhooks work while user is away; no transport-disconnect fixture. Sources: qm:nov07-readme.
Other device continuation [unknown] Other device continuation: The November first-party documentation and repository pass did not establish laptop-independent execution at the rubric's required scope. No installed-product fixture was run.
QM has per-scope sandbox computers. The local provider uses Docker containers, volumes and networks; cloud providers include microVMs. Native Git worktree isolation is not a product workspace option.
Scope
Surfaces: QM web workspace, QM Slack plugin, QM core and deployment CLI, QM Desktop Apple Silicon · Version: First-party sources checked 2026-11-07; pinned implementations retain their cited revision.; v0.1.18 (9c20219, 2026-11-11) for backfilled atoms · Plan: Not specified · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
generally-available
Delivery
native
Checked
2026-11-07 (15 days old)
Agent cross-check
2026-11-22
Documentation and pinned source inspection only; no hands-on scenario was run.
Other atomic questions remain unestablished: checkout, branch, os_sandbox, process, security_boundary.
12 atomic answers
Checkout [unknown] Checkout: The November first-party documentation and repository pass did not establish workspace and process isolation at the rubric's required scope. No installed-product fixture was run.
Branch [unknown] Branch: The November first-party documentation and repository pass did not establish workspace and process isolation at the rubric's required scope. No installed-product fixture was run.
Worktree [unsupported] The current sandbox/workspace model has no product-managed Git worktree provisioning; generic agent Git commands remain separate. Sources: qm:gaps-public-model.
Container [supported] The local provider provisions per-scope Docker containers with persistent home volumes and separate networks. Sources: qm:gaps-local-docker.
Vm [supported] DigitalOcean Managed Agents template yields a microVM with no managed agent loop; disk persists across pause/resume. Sources: qm:gap-preservation.
Os sandbox [unknown] Os sandbox: The November first-party documentation and repository pass did not establish workspace and process isolation at the rubric's required scope. No installed-product fixture was run.
Filesystem [partial] Dedicated blank worker computers; parent files are not copied. Sources: qm:nov07-swarms.
Process [unknown] Process: The November first-party documentation and repository pass did not establish workspace and process isolation at the rubric's required scope. No installed-product fixture was run.
Network [partial] The default auto posture denies private-network access; strict and dangerous do not. An optional egress-proxy service forces sandbox traffic through a proxy for supported backends. Sources: qm:b06-posture, qm:b06-deploy-dir.
Secrets [supported] Worker data/keychain access uses authorization scope; session grants do not automatically transfer. Sources: qm:nov07-swarms.
Security boundary [unknown] Security boundary: The November first-party documentation and repository pass did not establish workspace and process isolation at the rubric's required scope. No installed-product fixture was run.
Durable core state, provider snapshots and file publication have separate recovery boundaries.
Scope
Surfaces: QM web workspace, QM Slack plugin, QM core and deployment CLI, QM Desktop Apple Silicon · Version: First-party sources checked 2026-11-07; pinned implementations retain their cited revision.; v0.1.18 (9c20219, 2026-11-11) for backfilled atoms · Plan: Not specified · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
generally-available
Delivery
native
Checked
2026-11-07 (15 days old)
Agent cross-check
2026-11-22
The remaining atomic questions and the rubric scenario are unverified. Documentation is not a successful product test.
Only the named atomic facts are established by documentation. Remaining rubric scenarios and unknown answers were not demonstrated.
12 atomic answers
Client disconnect [unknown] Client disconnect: The November first-party documentation and repository pass did not establish recovery, expiry and continuity at the rubric's required scope. No installed-product fixture was run.
Worker crash [unknown] Worker crash: The November first-party documentation and repository pass did not establish recovery, expiry and continuity at the rubric's required scope. No installed-product fixture was run.
Service restart [partial] Durable outbox resumes reservations rather than allocating another worker. Sources: qm:nov07-swarms.
Expiry [supported] Modal computers have 24-hour lifetime; snapshot persistence/restore depends on configured provider/S3 options. Sources: qm:gap-preservation.
Process reconnect [unknown] Process reconnect: The November first-party documentation and repository pass did not establish recovery, expiry and continuity at the rubric's required scope. No installed-product fixture was run.
Task resume [unknown] Task resume: The November first-party documentation and repository pass did not establish recovery, expiry and continuity at the rubric's required scope. No installed-product fixture was run.
State reconstruction [partial] Mixed memory/Postgres stores are refused for swarms. Crash behavior untested. Sources: qm:nov07-swarms.
Context loss [supported] Cold restore may recover files without processes; provider pause/restart semantics differ. Sources: qm:gap-preservation.
Duplicate actions [supported] Subagent request keys recover the same child and run after a lost receipt and reject reuse for different work; message call IDs deduplicate retries. Sources: qm:b06-subagents.
Manual repair [unknown] Manual repair: The November first-party documentation and repository pass did not establish recovery, expiry and continuity at the rubric's required scope. No installed-product fixture was run.
Multi day continuity [unknown] Multi day continuity: The November first-party documentation and repository pass did not establish recovery, expiry and continuity at the rubric's required scope. No installed-product fixture was run.
Scoped computers retain installed tools and support provider-specific snapshots.
Scope
Surfaces: QM core and deployment CLI, QM web workspace · Version: First-party documentation/source checked 2026-11-07; exact pinned source revision is recorded in each citation. No installed-product fixture. · Plan: Not specified · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
unknown
Delivery
unknown
Checked
2026-11-07 (15 days old)
Agent cross-check
2026-11-10
Only the named atomic facts are established by documentation. Remaining rubric scenarios and unknown answers were not demonstrated.
Caches [unknown] Caches: The November first-party documentation and repository pass did not establish development environment reliability at the rubric's required scope. No installed-product fixture was run.
Snapshots [supported] Provider-specific snapshots preserve sandboxes: Modal checkpoints, E2B createSnapshot and Render golden snapshots. Sources: qm:gap-preservation.
Services [unknown] Services: The November first-party documentation and repository pass did not establish development environment reliability at the rubric's required scope. No installed-product fixture was run.
Ports [unknown] Ports: The November first-party documentation and repository pass did not establish development environment reliability at the rubric's required scope. No installed-product fixture was run.
Secrets [unknown] Secrets: The November first-party documentation and repository pass did not establish development environment reliability at the rubric's required scope. No installed-product fixture was run.
Duplicate installs [unknown] Duplicate installs: The November first-party documentation and repository pass did not establish development environment reliability at the rubric's required scope. No installed-product fixture was run.
Collisions [unknown] Collisions: The November first-party documentation and repository pass did not establish development environment reliability at the rubric's required scope. No installed-product fixture was run.
Remote setup [unknown] Remote setup: The November first-party documentation and repository pass did not establish development environment reliability at the rubric's required scope. No installed-product fixture was run.
Automatic repair [unknown] Automatic repair: The November first-party documentation and repository pass did not establish development environment reliability at the rubric's required scope. No installed-product fixture was run.
Swarm goals/time budgets and resource reconciliation have bounded failure behavior.
Scope
Surfaces: QM web workspace, QM Slack plugin, QM core and deployment CLI, QM Desktop Apple Silicon · Version: First-party sources checked 2026-11-07; pinned implementations retain their cited revision.; v0.1.18 (9c20219, 2026-11-11) for backfilled atoms · Plan: Not specified · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
unknown
Delivery
native
Checked
2026-11-07 (15 days old)
Agent cross-check
2026-11-22
The remaining atomic questions and the rubric scenario are unverified. Documentation is not a successful product test.
The swarms document gates this behind a feature flag and states no release stage.
Only the named atomic facts are established by documentation. Remaining rubric scenarios and unknown answers were not demonstrated.
8 atomic answers
Time limits [supported] Optional lifetimeMs and turnMs. Sources: qm:nov07-swarms.
Turn limits [unknown] Turn limits: The November first-party documentation and repository pass did not establish limits and failure handling at the rubric's required scope. No installed-product fixture was run.
Token limits [supported] Optional worker goal token_cap stops goal when spent; retries do not reinstall same goal. Sources: qm:gap-swarms.
Spend limits [supported] Per-scope daily and monthly USD caps with an org per-person default; at the cap new turns are refused until the UTC reset. Sources: qm:b06-spend-limits, qm:b06-rel-0116.
Timeouts [supported] Resource reconciliation has 30-second phase and 10-second provisioning-attempt deadlines; unfinished side effects retain slot/lock. Sources: qm:gap-swarms.
Retries [supported] Worker provisioning gets three attempts. Sources: qm:nov07-swarms.
Provider failures [unknown] Provider failures: The November first-party documentation and repository pass did not establish limits and failure handling at the rubric's required scope. No installed-product fixture was run.
Enforcement [partial] Agent/message/notification budgets reserve atomically. No bounded fixture was run. Sources: qm:nov07-swarms.
Operator error records and optional Sentry reporting expose logs and failure causes. Accuracy not fixture-tested.
Scope
Surfaces: QM core and deployment CLI, QM web workspace · Version: First-party documentation/source checked 2026-11-07; exact pinned source revision is recorded in each citation. No installed-product fixture. · Plan: Not specified · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
unknown
Delivery
unknown
Checked
2026-11-07 (15 days old)
Agent cross-check
2026-11-10
Only the named atomic facts are established by documentation. Remaining rubric scenarios and unknown answers were not demonstrated.
13 atomic answers
Logs [supported] Operator failures and exception stacks are recorded; configured Sentry adds event IDs. Sources: qm:gap-errors.
Traces [unknown] Traces: The November first-party documentation and repository pass did not establish truthful status and operational statistics at the rubric's required scope. No installed-product fixture was run.
Failure reasons [supported] Captured failures include category/code/message/scope/session; best-effort reporting is not a complete reliability ledger. Sources: qm:gap-errors.
Usage export [unknown] Usage export: The November first-party documentation and repository pass did not establish truthful status and operational statistics at the rubric's required scope. No installed-product fixture was run.
Task stats [unknown] Task stats: The November first-party documentation and repository pass did not establish truthful status and operational statistics at the rubric's required scope. No installed-product fixture was run.
Agent stats [unknown] Agent stats: The November first-party documentation and repository pass did not establish truthful status and operational statistics at the rubric's required scope. No installed-product fixture was run.
Project stats [unknown] Project stats: The November first-party documentation and repository pass did not establish truthful status and operational statistics at the rubric's required scope. No installed-product fixture was run.
Time stats [unknown] Time stats: The November first-party documentation and repository pass did not establish truthful status and operational statistics at the rubric's required scope. No installed-product fixture was run.
Failure status [unknown] Failure status: The November first-party documentation and repository pass did not establish truthful status and operational statistics at the rubric's required scope. No installed-product fixture was run.
Approval status [unknown] Approval status: The November first-party documentation and repository pass did not establish truthful status and operational statistics at the rubric's required scope. No installed-product fixture was run.
Reconnect consistency [unknown] Reconnect consistency: The November first-party documentation and repository pass did not establish truthful status and operational statistics at the rubric's required scope. No installed-product fixture was run.
Performance method [unknown] Performance method: The November first-party documentation and repository pass did not establish truthful status and operational statistics at the rubric's required scope. No installed-product fixture was run.
Responsiveness [unknown] Responsiveness: The November first-party documentation and repository pass did not establish truthful status and operational statistics at the rubric's required scope. No installed-product fixture was run.
QM estimates model spend per request from token usage and list prices and reports it by person, scope, cron and model, with export; caps stop new turns without alerts.
Scope
Surfaces: QM web workspace, QM core and deployment CLI · Version: v0.1.18 (9c20219, 2026-11-11) · Plan: Not specified · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
generally-available
Delivery
native
Checked
2026-11-21 (1 day old)
Agent cross-check
2026-11-22
Source inspection of v0.1.18 spend code; no deployment or billing reconciliation was run.
14 atomic answers
Task cost [unknown] Task cost: The November first-party documentation and repository pass did not establish per-task api and compute cost at the rubric's required scope. No installed-product fixture was run.
Session cost [partial] People see their own spend and admins see org spend by person, scope (room), cron and model; reports do not break cost down per individual session. Sources: qm:b06-spend-report, qm:b06-rel-0116.
Child cost [unknown] Child cost: The November first-party documentation and repository pass did not establish per-task api and compute cost at the rubric's required scope. No installed-product fixture was run.
Epic cost [unknown] Epic cost: The November first-party documentation and repository pass did not establish per-task api and compute cost at the rubric's required scope. No installed-product fixture was run.
Harness aggregation [unknown] Harness aggregation: The November first-party documentation and repository pass did not establish per-task api and compute cost at the rubric's required scope. No installed-product fixture was run.
Billed vs estimated [partial] Costs are labeled as QM estimates at list price that can differ from the bill; they are calculated from token usage and price cards, not read from provider bills. Sources: qm:b06-spend-ui, qm:b06-cost-calc.
Tokens [supported] Reports include calls and input, output, cache-read and cache-write tokens. Sources: qm:b06-spend-report.
Subscription allowance [unknown] Subscription allowance: The November first-party documentation and repository pass did not establish per-task api and compute cost at the rubric's required scope. No installed-product fixture was run.
Provider reconciliation [unsupported] A bounded search of the v0.1.18 spend, model and web UI code for invoice, reconcile, billing and provider usage-report calls found no import or reconciliation of provider bills. Sources: qm:nov22-spend-reconcile-search.
Compute cost [unknown] Compute cost: The November first-party documentation and repository pass did not establish per-task api and compute cost at the rubric's required scope. No installed-product fixture was run.
Refresh delay [unknown] Refresh delay: The November first-party documentation and repository pass did not establish per-task api and compute cost at the rubric's required scope. No installed-product fixture was run.
Alerts [partial] No spend alerts or notifications; at a configured cap new turns are refused with a message naming the limit. Sources: qm:b06-spend-limits.
Export [supported] GET /v1/spend/export returns spend rows with an export token. Sources: qm:b06-spend-report.
Drilldown [supported] Day or week series drill into person, scope, cron, model and live versus background spend. Sources: qm:b06-spend-report.
Swarm resource pools, durable cleanup and notification pools bound provisioning.
Scope
Surfaces: QM web workspace, QM Slack plugin, QM core and deployment CLI, QM Desktop Apple Silicon · Version: First-party sources checked 2026-11-07; pinned implementations retain their cited revision. · Plan: Not specified · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
unknown
Delivery
native
Checked
2026-11-07 (15 days old)
Agent cross-check
2026-11-07
The remaining atomic questions and the rubric scenario are unverified. Documentation is not a successful product test.
The swarms document gates this behind a feature flag and states no release stage.
Only the named atomic facts are established by documentation. Remaining rubric scenarios and unknown answers were not demonstrated.
12 atomic answers
Concurrency [partial] Default agents budget is a lifetime reservation limit, not measured CPU/RAM scheduling. Sources: qm:nov07-swarms.
Queues [supported] Durable outbox reserves and reconciles workers before delivery. Sources: qm:gap-swarms.
Cpu ram [unknown] Cpu ram: The November first-party documentation and repository pass did not establish compute-aware scheduling and verification at the rubric's required scope. No installed-product fixture was run.
Backpressure [supported] Four-slot resource pool and separate four-slot notification pool prevent resource cleanup from consuming delivery slots. Sources: qm:gap-swarms.
Host awareness [unknown] Host awareness: The November first-party documentation and repository pass did not establish compute-aware scheduling and verification at the rubric's required scope. No installed-product fixture was run.
Check reuse [unknown] Check reuse: The November first-party documentation and repository pass did not establish compute-aware scheduling and verification at the rubric's required scope. No installed-product fixture was run.
Check deduplication [unknown] Check deduplication: The November first-party documentation and repository pass did not establish compute-aware scheduling and verification at the rubric's required scope. No installed-product fixture was run.
Bounded tests [unknown] Bounded tests: The November first-party documentation and repository pass did not establish compute-aware scheduling and verification at the rubric's required scope. No installed-product fixture was run.
Fairness [supported] Each sweep selects at most sixteen pending swarms and advances pages so failed cleanup does not monopolize batch. Sources: qm:gap-swarms.
Recovery [supported] Durable reconciliation of reservations. Sources: qm:nov07-swarms.
Shared limits [unknown] Shared limits: The November first-party documentation and repository pass did not establish compute-aware scheduling and verification at the rubric's required scope. No installed-product fixture was run.
QM supports people collaborating with an agent in shared Slack/web rooms.
Scope
Surfaces: QM web workspace, QM Slack plugin, QM core and deployment CLI, QM Desktop Apple Silicon · Version: First-party sources checked 2026-11-07; pinned implementations retain their cited revision. · Plan: Not specified · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
generally-available
Delivery
native
Checked
2026-11-07 (15 days old)
Agent cross-check
2026-11-07
The remaining atomic questions and the rubric scenario are unverified. Documentation is not a successful product test.
Only the named atomic facts are established by documentation. Remaining rubric scenarios and unknown answers were not demonstrated.
11 atomic answers
Visibility [supported] Personal and shared scopes. Sources: qm:nov07-readme.
Discussion [supported] Slack channels, group messages and projects. Sources: qm:nov07-readme.
Comments [unknown] Comments: The November first-party documentation and repository pass did not establish live human collaboration at the rubric's required scope. No installed-product fixture was run.
Presence [unknown] Presence: The November first-party documentation and repository pass did not establish live human collaboration at the rubric's required scope. No installed-product fixture was run.
Coprompting [supported] Employees collaborate with the agent in shared channels, group messages and projects. Sources: qm:nov07-readme.
Ordering [unknown] Ordering: The November first-party documentation and repository pass did not establish live human collaboration at the rubric's required scope. No installed-product fixture was run.
Conflicts [unknown] Conflicts: The November first-party documentation and repository pass did not establish live human collaboration at the rubric's required scope. No installed-product fixture was run.
Attribution [supported] Each turn acts as the person with their credentials/permissions; shared scope remains explicit. Sources: qm:nov07-readme.
Permissions [supported] Scope-specific permissions and sharing grants. Sources: qm:nov07-readme.
Plan restrictions [unknown] Plan restrictions: The November first-party documentation and repository pass did not establish live human collaboration at the rubric's required scope. No installed-product fixture was run.
Owner online [unknown] Owner online: The November first-party documentation and repository pass did not establish live human collaboration at the rubric's required scope. No installed-product fixture was run.
Organization security posture and project membership controls are documented.
Scope
Surfaces: QM web workspace, QM Slack plugin, QM core and deployment CLI, QM Desktop Apple Silicon · Version: First-party sources checked 2026-11-07; pinned implementations retain their cited revision.; v0.1.18 (9c20219, 2026-11-11) for backfilled atoms · Plan: Not specified · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
generally-available
Delivery
native
Checked
2026-11-07 (15 days old)
Agent cross-check
2026-11-22
The remaining atomic questions and the rubric scenario are unverified. Documentation is not a successful product test.
9 atomic answers
Organization roles [partial] Admin controls organization configuration and sharing. Full role matrix unverified. Sources: qm:nov07-readme.
Project roles [partial] Fixed owner and member roles: members add members and set the icon; only the owner removes members or renames; no configurable roles. Sources: qm:b06-projects.
Task roles [unknown] Task roles: The November first-party documentation and repository pass did not establish roles and access boundaries at the rubric's required scope. No installed-product fixture was run.
Sso [supported] Deployment can use external OIDC sign-in at the public SSO front door instead of embedded email auth; provider implementation and enterprise policy enforcement untested. Sources: qm:gap-oidc, qm:gap-web.
Provisioning [unknown] Provisioning: The November first-party documentation and repository pass did not establish roles and access boundaries at the rubric's required scope. No installed-product fixture was run.
Unauthorized access [partial] Handlers return forbidden/not-found for capability restrictions; no unauthorized-account test. Sources: qm:nov07-projects.
Revocation [supported] An admin previews or applies one-step offboarding; each step is audited and reactivation exists. Sources: qm:b06-offboard, qm:b06-rel-0116.
Plan scope [unknown] Plan scope: The November first-party documentation and repository pass did not establish roles and access boundaries at the rubric's required scope. No installed-product fixture was run.
QM has posture-based command rules and exact-argument single-use MCP approvals.
Scope
Surfaces: QM web workspace, QM Slack plugin, QM core and deployment CLI, QM Desktop Apple Silicon · Version: First-party sources checked 2026-11-07; pinned implementations retain their cited revision. · Plan: Not specified · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
generally-available
Delivery
native
Checked
2026-11-07 (15 days old)
Agent cross-check
2026-11-10
The remaining atomic questions and the rubric scenario are unverified. Documentation is not a successful product test.
Only the named atomic facts are established by documentation. Remaining rubric scenarios and unknown answers were not demonstrated.
14 atomic answers
Command [supported] Predeclared command hard denials apply in every posture, including Dangerous. Sources: qm:nov07-readme.
Tool [supported] Strict mode asks for each tool call except turn enders. Sources: qm:nov07-readme.
Network [supported] Auto mode blocks private-network access. Sources: qm:nov07-readme.
Secret [supported] Per-user MCP uses encrypted actor credential keychain and no cross-user credential fallback. Sources: qm:gap-mcp.
Delivery [unknown] Delivery: The November first-party documentation and repository pass did not establish approvals and temporary access at the rubric's required scope. No installed-product fixture was run.
Approver identity [supported] Approval grants belong only to the session that received them; swarm workers never inherit the root session's command or security-screen approval grants and must obtain their own approval. Sources: qm:nov07-swarms, qm:gap-swarms.
Lifetime [supported] MCP approval binds exact arguments and is good for one call. Sources: qm:gap-mcp.
Allow [supported] Configured MCP approval policy may require every call or annotated destructive calls. Sources: qm:gap-mcp.
Deny [unknown] Deny: The November first-party documentation and repository pass did not establish approvals and temporary access at the rubric's required scope. No installed-product fixture was run.
Revoke [unknown] Revoke: The November first-party documentation and repository pass did not establish approvals and temporary access at the rubric's required scope. No installed-product fixture was run.
Tunnels [unknown] Tunnels: The November first-party documentation and repository pass did not establish approvals and temporary access at the rubric's required scope. No installed-product fixture was run.
Defaults [supported] Auto security posture and Isolated sharing posture. Sources: qm:nov07-readme.
Durable shared session snapshots preserve selected visible history, separate from raw tool/audit history.
Scope
Surfaces: QM core and deployment CLI, QM web workspace · Version: First-party documentation/source checked 2026-11-07; exact pinned source revision is recorded in each citation. No installed-product fixture.; v0.1.18 (9c20219, 2026-11-11) for backfilled atoms · Plan: Not specified · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
unknown
Delivery
unknown
Checked
2026-11-07 (15 days old)
Agent cross-check
2026-11-22
Only the named atomic facts are established by documentation. Remaining rubric scenarios and unknown answers were not demonstrated.
11 atomic answers
Actions [supported] Every tool call is committed to the session item log, and an audit log records approvals, security flags, credentials, connectors, sharing, sandbox, session and admin actions for admins. Sources: qm:b06-audit, qm:b06-readme.
Approvals [unknown] Approvals: The November first-party documentation and repository pass did not establish decision and activity history at the rubric's required scope. No installed-product fixture was run.
Edits [unknown] Edits: The November first-party documentation and repository pass did not establish decision and activity history at the rubric's required scope. No installed-product fixture was run.
Discussion [supported] Share snapshot includes visible human messages, final replies and attachments. Sources: qm:gap-share.
Decisions [unknown] Decisions: The November first-party documentation and repository pass did not establish decision and activity history at the rubric's required scope. No installed-product fixture was run.
Cross user persistence [unknown] Cross user persistence: The November first-party documentation and repository pass did not establish decision and activity history at the rubric's required scope. No installed-product fixture was run.
Cross session persistence [supported] Fresh share links retain original snapshot content and durable copied attachments. Sources: qm:gap-share.
Export [supported] Read-only shared webpage and copied attachment downloads; no full transcript export guarantee. Sources: qm:gap-share.
Mutability [supported] Shared snapshots have no update/revoke controls; access depends on creator retaining entitlement. Sources: qm:gap-share.
Retention [unknown] Retention: The November first-party documentation and repository pass did not establish decision and activity history at the rubric's required scope. No installed-product fixture was run.
Integrity [unknown] Integrity: The November first-party documentation and repository pass did not establish decision and activity history at the rubric's required scope. No installed-product fixture was run.
QM displays conversation artifacts, files and approvals without an integrated proposed-code diff review interface in the inspected client.
Scope
Surfaces: QM web workspace, QM Slack plugin, QM core and deployment CLI, QM Desktop Apple Silicon · Version: Not specified · Plan: Not specified · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
generally-available
Delivery
native
Checked
2026-11-13 (9 days old)
Agent cross-check
Not separately cross-checked
Documentation and pinned source inspection only; no hands-on scenario was run.
Pending reviews [unknown] Pending reviews: The November first-party documentation and repository pass did not establish review experience and guidance at the rubric's required scope. No installed-product fixture was run.
Change understanding [unsupported] The inspected web client has no proposed-code diff review surface. Configuration text differences and ordinary file viewers are outside this code-review filter. Sources: qm:gaps-public-model.
Evidence navigation [unknown] Evidence navigation: The November first-party documentation and repository pass did not establish review experience and guidance at the rubric's required scope. No installed-product fixture was run.
Comments [unknown] Comments: The November first-party documentation and repository pass did not establish review experience and guidance at the rubric's required scope. No installed-product fixture was run.
Request changes [unknown] Request changes: The November first-party documentation and repository pass did not establish review experience and guidance at the rubric's required scope. No installed-product fixture was run.
Shipping guidance [unknown] Shipping guidance: The November first-party documentation and repository pass did not establish review experience and guidance at the rubric's required scope. No installed-product fixture was run.
Effort [unknown] Effort: The November first-party documentation and repository pass did not establish review experience and guidance at the rubric's required scope. No installed-product fixture was run.
Missed evidence [unknown] Missed evidence: The November first-party documentation and repository pass did not establish review experience and guidance at the rubric's required scope. No installed-product fixture was run.
Keyboard [unknown] Keyboard: The November first-party documentation and repository pass did not establish review experience and guidance at the rubric's required scope. No installed-product fixture was run.
Narrow screen [unknown] Narrow screen: The November first-party documentation and repository pass did not establish review experience and guidance at the rubric's required scope. No installed-product fixture was run.
Context switching [unknown] Context switching: The November first-party documentation and repository pass did not establish review experience and guidance at the rubric's required scope. No installed-product fixture was run.
Roles [unknown] Roles: The November first-party documentation and repository pass did not establish review experience and guidance at the rubric's required scope. No installed-product fixture was run.
Retained context [unknown] Retained context: The November first-party documentation and repository pass did not establish review experience and guidance at the rubric's required scope. No installed-product fixture was run.
Slack and web share identity and configuration; full colleague takeover is unverified.
Scope
Surfaces: QM web workspace, QM Slack plugin, QM core and deployment CLI, QM Desktop Apple Silicon · Version: First-party sources checked 2026-11-07; pinned implementations retain their cited revision. · Plan: Not specified · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
generally-available
Delivery
native
Checked
2026-11-07 (15 days old)
Agent cross-check
2026-11-07
The remaining atomic questions and the rubric scenario are unverified. Documentation is not a successful product test.
12 atomic answers
Ongoing takeover [unknown] Ongoing takeover: The November first-party documentation and repository pass did not establish colleague takeover and continuity at the rubric's required scope. No installed-product fixture was run.
Same task [unknown] Same task: The November first-party documentation and repository pass did not establish colleague takeover and continuity at the rubric's required scope. No installed-product fixture was run.
Session history [partial] Postgres history and shared identity; live authorized takeover was not tested. Sources: qm:nov07-readme.
Decisions [unknown] Decisions: The November first-party documentation and repository pass did not establish colleague takeover and continuity at the rubric's required scope. No installed-product fixture was run.
Artifacts [unknown] Artifacts: The November first-party documentation and repository pass did not establish colleague takeover and continuity at the rubric's required scope. No installed-product fixture was run.
Permissions [unknown] Permissions: The November first-party documentation and repository pass did not establish colleague takeover and continuity at the rubric's required scope. No installed-product fixture was run.
Runtime context [unknown] Runtime context: The November first-party documentation and repository pass did not establish colleague takeover and continuity at the rubric's required scope. No installed-product fixture was run.
Owner disconnect [unknown] Owner disconnect: The November first-party documentation and repository pass did not establish colleague takeover and continuity at the rubric's required scope. No installed-product fixture was run.
Ownership [unknown] Ownership: The November first-party documentation and repository pass did not establish colleague takeover and continuity at the rubric's required scope. No installed-product fixture was run.
Attribution [unknown] Attribution: The November first-party documentation and repository pass did not establish colleague takeover and continuity at the rubric's required scope. No installed-product fixture was run.
Context loss [unknown] Context loss: The November first-party documentation and repository pass did not establish colleague takeover and continuity at the rubric's required scope. No installed-product fixture was run.
Harness transfer [unknown] Harness transfer: The November first-party documentation and repository pass did not establish colleague takeover and continuity at the rubric's required scope. No installed-product fixture was run.
Published Files retain artifacts after sandbox retirement.
Scope
Surfaces: QM core and deployment CLI, QM web workspace · Version: First-party documentation/source checked 2026-11-07; exact pinned source revision is recorded in each citation. No installed-product fixture.; v0.1.18 (9c20219, 2026-11-11) for backfilled atoms · Plan: Not specified · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
unknown
Delivery
unknown
Checked
2026-11-07 (15 days old)
Agent cross-check
2026-11-22
Only the named atomic facts are established by documentation. Remaining rubric scenarios and unknown answers were not demonstrated.
13 atomic answers
Diffs [unknown] Diffs: The November first-party documentation and repository pass did not establish retained artifacts and outputs at the rubric's required scope. No installed-product fixture was run.
Documents [supported] Files publishes arbitrary named bytes with MIME metadata, including documented PDF example. Sources: qm:gap-files.
Screenshots [unknown] Screenshots: The November first-party documentation and repository pass did not establish retained artifacts and outputs at the rubric's required scope. No installed-product fixture was run.
Recordings [unknown] Recordings: The November first-party documentation and repository pass did not establish retained artifacts and outputs at the rubric's required scope. No installed-product fixture was run.
Previews [partial] Agents publish internal web apps visible to the owner and people it is shared with, with optional admin-gated public links; no per-change preview deployment of a repository is documented. Sources: qm:b06-apps, qm:b06-readme.
Test outputs [unknown] Test outputs: The November first-party documentation and repository pass did not establish retained artifacts and outputs at the rubric's required scope. No installed-product fixture was run.
Reviewer outputs [unknown] Reviewer outputs: The November first-party documentation and repository pass did not establish retained artifacts and outputs at the rubric's required scope. No installed-product fixture was run.
Gallery [unknown] Gallery: The November first-party documentation and repository pass did not establish retained artifacts and outputs at the rubric's required scope. No installed-product fixture was run.
Task links [supported] Published file belongs to conversation scope and uses actor/conversation-bound upload state. Sources: qm:gap-files.
Revision links [unknown] Revision links: The November first-party documentation and repository pass did not establish retained artifacts and outputs at the rubric's required scope. No installed-product fixture was run.
Persistence [supported] Completed Files bytes and metadata are independent of sandbox lifetime. Sources: qm:gap-files.
Child findings [unknown] Child findings: The November first-party documentation and repository pass did not establish retained artifacts and outputs at the rubric's required scope. No installed-product fixture was run.
Prompt leakage [unknown] Prompt leakage: The November first-party documentation and repository pass did not establish retained artifacts and outputs at the rubric's required scope. No installed-product fixture was run.
QM advertises running tests and monitoring repository CI through the agent. Enforced delivery gates remain unknown.
Scope
Surfaces: QM core and deployment CLI, QM web workspace · Version: First-party documentation/source checked 2026-11-07; exact pinned source revision is recorded in each citation. No installed-product fixture. · Plan: Not specified · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
unknown
Delivery
unknown
Checked
2026-11-07 (15 days old)
Agent cross-check
2026-11-07
Only the named atomic facts are established by documentation. Remaining rubric scenarios and unknown answers were not demonstrated.
11 atomic answers
Tests [supported] README lists working in a repo to run tests; no test execution observed. Sources: qm:nov07-readme.
Lint [unknown] Lint: The November first-party documentation and repository pass did not establish verification and spec gates at the rubric's required scope. No installed-product fixture was run.
Types [unknown] Types: The November first-party documentation and repository pass did not establish verification and spec gates at the rubric's required scope. No installed-product fixture was run.
Independent review [unknown] Independent review: The November first-party documentation and repository pass did not establish verification and spec gates at the rubric's required scope. No installed-product fixture was run.
Spec checks [unknown] Spec checks: The November first-party documentation and repository pass did not establish verification and spec gates at the rubric's required scope. No installed-product fixture was run.
Required checks [unknown] Required checks: The November first-party documentation and repository pass did not establish verification and spec gates at the rubric's required scope. No installed-product fixture was run.
Failure blocking [unknown] Failure blocking: The November first-party documentation and repository pass did not establish verification and spec gates at the rubric's required scope. No installed-product fixture was run.
Requirement conflicts [unknown] Requirement conflicts: The November first-party documentation and repository pass did not establish verification and spec gates at the rubric's required scope. No installed-product fixture was run.
Configured policy [unknown] Configured policy: The November first-party documentation and repository pass did not establish verification and spec gates at the rubric's required scope. No installed-product fixture was run.
Enforced policy [unknown] Enforced policy: The November first-party documentation and repository pass did not establish verification and spec gates at the rubric's required scope. No installed-product fixture was run.
QM advertises agent work in repositories including PR creation and CI monitoring.
Scope
Surfaces: QM core and deployment CLI, QM web workspace · Version: First-party documentation/source checked 2026-11-07; exact pinned source revision is recorded in each citation. No installed-product fixture. · Plan: Not specified · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
unknown
Delivery
unknown
Checked
2026-11-07 (15 days old)
Agent cross-check
2026-11-07
Only the named atomic facts are established by documentation. Remaining rubric scenarios and unknown answers were not demonstrated.
9 atomic answers
Branches [unknown] Branches: The November first-party documentation and repository pass did not establish git and pull request workflow at the rubric's required scope. No installed-product fixture was run.
Worktrees [unknown] Worktrees: The November first-party documentation and repository pass did not establish git and pull request workflow at the rubric's required scope. No installed-product fixture was run.
Commits [unknown] Commits: The November first-party documentation and repository pass did not establish git and pull request workflow at the rubric's required scope. No installed-product fixture was run.
Comments [unknown] Comments: The November first-party documentation and repository pass did not establish git and pull request workflow at the rubric's required scope. No installed-product fixture was run.
Ci response [supported] CI monitoring documented; automated repair or merge gating not established. Sources: qm:nov07-readme.
Rebase [unknown] Rebase: The November first-party documentation and repository pass did not establish git and pull request workflow at the rubric's required scope. No installed-product fixture was run.
Conflicts [unknown] Conflicts: The November first-party documentation and repository pass did not establish git and pull request workflow at the rubric's required scope. No installed-product fixture was run.
Product state [unknown] Product state: The November first-party documentation and repository pass did not establish git and pull request workflow at the rubric's required scope. No installed-product fixture was run.
QM repository is MIT. The headless core server is in the same MIT repository.
Scope
Surfaces: QM web workspace, QM Slack plugin, QM core and deployment CLI, QM Desktop Apple Silicon · Version: First-party sources checked 2026-11-07; pinned implementations retain their cited revision.; v0.1.18 (9c20219, 2026-11-11) for backfilled atoms · Plan: Not specified · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
generally-available
Delivery
native
Checked
2026-11-07 (15 days old)
Agent cross-check
2026-11-22
The remaining atomic questions and the rubric scenario are unverified. Documentation is not a successful product test.
6 atomic answers
Client license [supported] MIT, subject to component notices. Sources: qm:nov07-license.
Server license [supported] MIT: the headless core (src/) ships in the same MIT-licensed repository as the CLI and clients. Sources: qm:b06-license.
Hosted extensions [unknown] Hosted extensions: The November first-party documentation and repository pass did not establish source and license at the rubric's required scope. No installed-product fixture was run.
Source visibility [supported] Public repository. Sources: qm:nov07-license.
Hosted parity [unknown] Hosted parity: The November first-party documentation and repository pass did not establish source and license at the rubric's required scope. No installed-product fixture was run.
Vendor dependencies [partial] Model and infrastructure accounts remain dependencies. Hosted third-party QM is separate. Sources: qm:nov07-readme.
Export [supported] Files publication creates durable downloadable outputs; sandbox retirement requires publishing useful files or using version control. Sources: qm:gap-files, qm:nov07-swarms.
Import [unknown] Import: The November first-party documentation and repository pass did not establish hosting and exit at the rubric's required scope. No installed-product fixture was run.
Formats [supported] Published bytes with file metadata; share snapshots separately contain copied attachments. Sources: qm:gap-files, qm:gap-share.
Cancellation [unknown] Cancellation: The November first-party documentation and repository pass did not establish hosting and exit at the rubric's required scope. No installed-product fixture was run.
Account independence [supported] Setup uses the operator's own cloud account, email sender and identity provider; no QM or YC vendor account is part of deployment. Sources: qm:b06-getting-started.
History portability [unknown] History portability: The November first-party documentation and repository pass did not establish hosting and exit at the rubric's required scope. No installed-product fixture was run.
QM telemetry is deployment-configured with separate analytics and backend/browser error controls.
Scope
Surfaces: QM core and deployment CLI, QM web workspace · Version: First-party documentation/source checked 2026-11-07; exact pinned source revision is recorded in each citation. No installed-product fixture.; v0.1.18 (9c20219, 2026-11-11) for backfilled atoms · Plan: Not specified · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
unknown
Delivery
unknown
Checked
2026-11-07 (15 days old)
Agent cross-check
2026-11-22
Only the named atomic facts are established by documentation. Remaining rubric scenarios and unknown answers were not demonstrated.
15 atomic answers
Code data [partial] Conversation, memory, files and workspace data live in the operator's Postgres, object storage and sandboxes; model and browser providers receive what is sent to them. Hosted third-party options are outside this scope. Sources: qm:b06-security, qm:b06-readme.
Prompts [unknown] Prompts: The November first-party documentation and repository pass did not establish data handling and telemetry at the rubric's required scope. No installed-product fixture was run.
Credentials [unknown] Credentials: The November first-party documentation and repository pass did not establish data handling and telemetry at the rubric's required scope. No installed-product fixture was run.
Logs [supported] Browser Sentry errors carry full message/stack and authenticated identity; optional timing includes request URLs. Sources: qm:gap-web.
Artifacts [unknown] Artifacts: The November first-party documentation and repository pass did not establish data handling and telemetry at the rubric's required scope. No installed-product fixture was run.
Retention [unknown] Retention: The November first-party documentation and repository pass did not establish data handling and telemetry at the rubric's required scope. No installed-product fixture was run.
Deletion [unknown] Deletion: The November first-party documentation and repository pass did not establish data handling and telemetry at the rubric's required scope. No installed-product fixture was run.
Training [unknown] Training: The November first-party documentation and repository pass did not establish data handling and telemetry at the rubric's required scope. No installed-product fixture was run.
Residency [unknown] Residency: The November first-party documentation and repository pass did not establish data handling and telemetry at the rubric's required scope. No installed-product fixture was run.
Subprocessors [unknown] Subprocessors: The November first-party documentation and repository pass did not establish data handling and telemetry at the rubric's required scope. No installed-product fixture was run.
Telemetry defaults [supported] No PostHog key means no analytics; no browser DSN means no browser error reporting. Trace rates default zero. Sources: qm:gap-web.
Telemetry controls [supported] Unset POSTHOG_API_KEY and SENTRY_BROWSER_DSN for analytics/browser errors; backend reporting separately disabled by removing SENTRY_DSN and redeploying. Sources: qm:gap-web, qm:gap-errors.
Consent prompt [unknown] Consent prompt: The November first-party documentation and repository pass did not establish data handling and telemetry at the rubric's required scope. No installed-product fixture was run.
Provider separation [supported] Model keys stay server-side and never reach the browser; deployments run in the operator's own cloud with their own models and keys. Sources: qm:gap-web, qm:nov07-readme.
QM is MIT open source and self-hosted in your own cloud with your own model keys; YC publishes no paid plan, and the hosted versions listed come from third parties with no price in the README.
Scope
Surfaces: QM web workspace, QM Slack plugin, QM core and deployment CLI, QM Desktop Apple Silicon · Version: First-party pricing sources read 2026-11-10 · Plan: Not specified · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
unknown
Delivery
unknown
Checked
2026-11-10 (12 days old)
Agent cross-check
2026-11-10
First-party pricing pages, terms and licences read 2026-11-10; no purchase, billing or authenticated account test.
12 atomic answers
Currency [unknown] No first-party source states currency for a paid plan. Checked: qm.ycombinator.com, yc-software/qm README and LICENSE. No pricing page or paid plan was found, but that does not prove none exists.
Interval [unknown] No first-party source states interval for a paid plan. Checked: qm.ycombinator.com, yc-software/qm README and LICENSE. No pricing page or paid plan was found, but that does not prove none exists.
Seats [unknown] No first-party source states seats for a paid plan. Checked: qm.ycombinator.com, yc-software/qm README and LICENSE. No pricing page or paid plan was found, but that does not prove none exists.
Seat minimum [unknown] No first-party source states seat minimum for a paid plan. Checked: qm.ycombinator.com, yc-software/qm README and LICENSE. No pricing page or paid plan was found, but that does not prove none exists.
Workspace fees [unknown] No first-party source states workspace fees for a paid plan. Checked: qm.ycombinator.com, yc-software/qm README and LICENSE. No pricing page or paid plan was found, but that does not prove none exists.
Included usage [unknown] No first-party source states included usage for a paid plan. Checked: qm.ycombinator.com, yc-software/qm README and LICENSE. No pricing page or paid plan was found, but that does not prove none exists.
Credits [unknown] No first-party source states credits for a paid plan. Checked: qm.ycombinator.com, yc-software/qm README and LICENSE. No pricing page or paid plan was found, but that does not prove none exists.
Trial [unknown] No first-party source states trial for a paid plan. Checked: qm.ycombinator.com, yc-software/qm README and LICENSE. No pricing page or paid plan was found, but that does not prove none exists.
Overages [unknown] No first-party source states overages for a paid plan. Checked: qm.ycombinator.com, yc-software/qm README and LICENSE. No pricing page or paid plan was found, but that does not prove none exists.
Taxes [unknown] No first-party source states taxes for a paid plan. Checked: qm.ycombinator.com, yc-software/qm README and LICENSE. No pricing page or paid plan was found, but that does not prove none exists.
Model cost [supported] You bring your own models and keys, so those providers bill for model usage. Sources: qm:readme-nov10.
Compute cost [partial] QM runs in your own cloud, so infrastructure costs fall on your cloud account. The README gives no amounts. Sources: qm:readme-nov10.
QM is distributed as an MIT-licensed npm package and source for operator-run deployment; README links a separate third-party hosted version. The latest stable release is pre-1.0 v0.1.18 (2026-11-11); v0.1.19 (2026-11-12) is a prerelease. v0.1.16 removed legacy harnesses, storage and settings.
Scope
Surfaces: QM core and deployment CLI, QM web workspace · Version: First-party documentation/source checked 2026-11-07; exact pinned source revision is recorded in each citation. No installed-product fixture.; v0.1.18 (9c20219, 2026-11-11) for backfilled atoms · Plan: Not specified · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
unknown
Delivery
unknown
Checked
2026-11-07 (15 days old)
Agent cross-check
2026-11-22
Only the named atomic facts are established by documentation. Remaining rubric scenarios and unknown answers were not demonstrated.
Access restrictions [supported] Operator deployment is separate from third-party hosted QM; own credentials and infrastructure required. Sources: qm:nov07-readme.
Support [partial] README routes vulnerability reports privately through SECURITY.md (not public issues) and takes contributions as human-written ADR text; no general support channel or response commitment is stated. Sources: qm:nov07-readme.
Response commitments [unknown] Response commitments: The November first-party documentation and repository pass did not establish availability and support at the rubric's required scope. No installed-product fixture was run.
Status history [unknown] Status history: The November first-party documentation and repository pass did not establish availability and support at the rubric's required scope. No installed-product fixture was run.
Deprecation [supported] v0.1.16 release notes list breaking removals: multiple harnesses, non-Postgres storage and several legacy features and settings. Sources: qm:b06-rel-0116.
Export options [unknown] Export options: The November first-party documentation and repository pass did not establish availability and support at the rubric's required scope. No installed-product fixture was run.
QM is MIT-licensed software an organization deploys in its own cloud with its own model keys. The README and licence state no price; the README invites larger companies to request a hosted version through a form. Cloud and model costs are the operator's.
Scope
Surfaces: QM core and deployment CLI · Version: Release v0.1.17 · Plan: Not specified · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
generally-available
Delivery
native
Checked
2026-11-10 (12 days old)
Agent cross-check
2026-11-10
Terms of the requested hosted version and third-party hosted offers were not checked. No installed-product test was run.
10 atomic answers
Ongoing free [supported] The software is MIT-licensed and free to deploy; the README and licence state no QM price or paid plan. Sources: qm:b4-license, qm:b4-readme.
Trial [unknown] Trial: The November first-party documentation and repository pass did not establish useful free tier and evaluation access at the rubric's required scope. No installed-product fixture was run.
Credits trial [unknown] Credits trial: The November first-party documentation and repository pass did not establish useful free tier and evaluation access at the rubric's required scope. No installed-product fixture was run.
Self host cost [partial] Self-deployment in the operator's own cloud carries no QM fee; cloud and model provider costs are the operator's and are not quantified. Sources: qm:b4-readme.
Paid only [unsupported] Not paid-only: the MIT source is free to deploy. Sources: qm:b4-license, qm:b4-readme.
Early access [unknown] Early access: The November first-party documentation and repository pass did not establish useful free tier and evaluation access at the rubric's required scope. No installed-product fixture was run.
Free scenarios [unknown] Free scenarios: The November first-party documentation and repository pass did not establish useful free tier and evaluation access at the rubric's required scope. No installed-product fixture was run.
Card required [unknown] Card required: The November first-party documentation and repository pass did not establish useful free tier and evaluation access at the rubric's required scope. No installed-product fixture was run.
Usage caps [unknown] Usage caps: The November first-party documentation and repository pass did not establish useful free tier and evaluation access at the rubric's required scope. No installed-product fixture was run.
Paid evaluation [unknown] Paid evaluation: The November first-party documentation and repository pass did not establish useful free tier and evaluation access at the rubric's required scope. No installed-product fixture was run.
Pi is the current core agent loop. Postgres holds durable session state; personal/shared scopes have files, memory, skills, permissions and background work. Operator deploys with own cloud/models/keys.
Kind
documented
Locator
Overview, setup, features and component boundaries
QM Desktop 0.1.6 (GitHub pre-release, 2026-11-06) is a signed/notarized Apple Silicon ZIP with back/forward navigation, Cmd+N and pane-control fixes; existing installs update through the desktop feed.
Web UI has phone layout and installable PWA. POSTHOG_API_KEY enables browser/core analytics; no key means no analytics requests. SENTRY_BROWSER_DSN enables browser errors and unset disables it; backend DSN never used as browser fallback. Tracing defaults off. PostHog replay follows project settings.
Kind
documented
Locator
On a phone; Optional analytics; Browser error reporting
The published Desktop 0.1.6 download is an Apple Silicon Mac ZIP. The desktop README also describes local prototype packaging and Windows/Linux shortcuts, which are not published Windows/Linux releases. Inspection of the public client source roots and release clients found desktop, web/PWA and Slack clients, with no native iOS or Android application. Phone use is the installable browser build.
Kind
documented
Locator
Desktop connection and release distribution; plugins/web-ui/README.md On a phone; desktop-v0.1.6 assets
The active core uses the Pi coding-agent library for its model loop. The current runtime has no client-selectable Claude Code, Codex, Cursor, Gemini CLI, OpenCode, Grok, Aider or Antigravity harness adapter. Provider API and subscription choices select model access within Pi rather than a different coding-agent CLI.
Kind
source-inspected
Locator
Pi coding-agent imports and run loop; README Architecture; src/harness and active wiring
Headless core (API, identity, policy, scheduler) runs the Pi agent loop for every turn against Postgres and per-scope sandboxes. Setup: an agent follows the deployment guide; DigitalOcean, E2B and Render offer one-click templates; Agent 37 is a third-party fully hosted option; YC offers an interest form for a hosted version, not a service. Features: web apps published to chosen people, skill packs imported from git, crons, watches and inbound webhooks. Auto posture (default) blocks private-network access; the agent acts as the person and its actions are audited. Org config, custom tools, skills and sandbox image live in a deployment directory.
Kind
documented
Locator
Setup; Features; Architecture; How it works; Security and secrets
Spend visibility (people see what their work costs; admins set spend caps), one-step offboarding, and Breaking: one agent harness (Claude via Pi), Postgres-only storage, several legacy features and settings removed.
A runtime migration drops approved_harness_configs and strips harnessId from model, cron, subagent, fallback and swarm configs: there is no per-run harness choice; every turn uses the built-in Pi coding agent.
Settings AI access explicitly offers Company, Claude and ChatGPT/Codex accounts. Users can sign in with a subscription or choose an API key; the selection applies to human chat turns on web and Slack, while background tasks retain company access. The implementation exchanges and refreshes native provider OAuth credentials. These account choices do not add Claude Code or Codex as coding harnesses.
Kind
documented
Locator
Personal AI accounts; src/model/subscription-oauth.ts and codex-device-login.ts
POST /v1/webhooks creates a webhook for a person; POST /v1/webhooks/incoming/:id receives verified deliveries that wake an agent turn; list, events and update routes exist.
Administrators register HTTP MCP servers; agents cannot change registration. Tools can use shared or per-user encrypted credentials with OAuth/PKCE; calls re-resolve actor credentials and never fall back to another user. Approval is exact-argument one-call, controlled by annotations/all/none.
sandbox/tools/<id>/tool.json plus binaries add custom tools and sandbox/skills/<id>/SKILL.md adds skills; plugins/ adds services. qm up syncs them to core as a versioned, audited deployment layer. An optional egress-proxy service forces sandbox traffic through a proxy that relays audit records, except exempt backends.
Kind
documented
Locator
Layout; Tool descriptors; Delivery and pins; Sandbox egress proxy
An org admin registers a git repository of SKILL.md files as a pack at a pinned ref, browses it and imports eligible skills into chosen scopes; updates bump the ref and re-import; admin routes are audited.
Electron client for an existing QM web deployment that runs the same web UI in a sandboxed window; does not bundle the backend. The macOS build is an unsigned local prototype.
iOS 18+ SwiftUI client; product screens, navigation, editors and conversation controls are native, with no embedded WebKit product UI; uses existing authenticated APIs and runs no agent on the phone. Built from source with Xcode.
Built-in memory has stable record IDs, sensitivity, source scope/session and provenance flags. Revisions are authoritative in Postgres; edits require revision checks, clearing does not erase historical revisions. Access rechecks sources on every read; audience change advances replay cutoff while transcripts/audit remain.
Kind
documented
Locator
Capture and curation; Fresh reads; Retained context
Bounded inspection of the current API routes, core state and web UI for issue/task/todo CRUD and code-diff review found agent conversations/runs, schedules and approvals, but no product-owned independent issue tracker or proposed-code diff review surface. The sandbox providers expose scoped computers rather than native Git worktree provisioning; agent shell commands can still operate Git independently.
Kind
source-inspected
Locator
Public API route registration; src/core/orchestrator; src/api/routes; plugins/web-ui/src; sandbox providers
Loop (Inbox) items carry status (queued, in_progress, ready, shipped, failed, skipped) and triage priority (urgent, high, normal, low). The inbox_loops feature flag defaults off and gates Inbox and Loops per personal scope.
A Loop's ledger is a durable queue of work items. POST /v1/loops/:id/items upserts items, GET lists them with counts per state, and item actions edit the proposal, dismiss or reopen an item or run the source's ship action; a follow-up thread can be attached per item. Item, inbox and action routes return feature_disabled unless the inbox_loops flag is on for the person's scope.
Crons take a cron expression with timezone, an everyMs interval or a first-fire time; the core scheduler fires them on the deployment without a client; /v1/crons creates and lists them.
The local sandbox provider provisions per-scope Docker containers, persistent home volumes and separate Docker networks and launches processes inside them. The documented local build path can run agent tools on an operator computer. This is a local Docker deployment, distinct from the Mac desktop client, which does not bundle a backend.
Kind
source-inspected
Locator
createLocalSandbox, provision and per-scope container/volume/network names; scripts/local-sandbox-build.sh
Provider-specific snapshots/pause behavior differs. Modal default one core/2 GiB and 24-hour lifetime; portable tar recovery needs configured S3 bucket. DigitalOcean Managed Agents sandbox template is a microVM with persistent disk across pause/resume. Cold recovery may restore files without processes.
auto (default) denies private networks without tool approvals; strict requires approval for every tool call; dangerous has neither gate. Only auto sets denyPrivateNetworks.
Reusing a request key recovers the same child and initial run after a lost receipt; using the key for different work is rejected. Stable call IDs deduplicate message retries.
Per-scope dailyUsd and monthlyUsd limits with an org per-person default; at the cap new turns are refused with a message until the UTC reset. No threshold alert or notification path exists in the module.
SENTRY_DSN enables backend exception reporting and unset disables it. Error context/stacks are unredacted. Profiling/log/replay disabled by default; optional traces have data scrubbing and sampling. Disable reporting by removing DSN and redeploying.
Admin and self spend reports give cost, calls and input/output/cache tokens by day or week, broken down by person, scope, cron, model, live versus background; GET /v1/spend/export exports rows with an export token. Reports group by scope and cron, not by individual session.
Within the named v0.1.18 spend/model/UI paths, spend rows come from per-request costUsd calculated from token usage and the model price card, with no provider-bill or invoice import/reconciliation path found. Reconcile functions elsewhere do not touch spend; this finding does not enumerate every unrelated reconcile function. The billing field in model-route.ts labels which key (gateway, org or personal) a request is billed to.
Kind
source-inspected
Locator
Searched src/ and plugins/web-ui/src at 9c20219 for invoice, reconcil, billing and provider usage/cost-report calls; spend files src/api/routes/admin/spend.ts, src/sessions/session-spend.ts, src/ratelimit/spend-limits.ts, src/model/model-runtime.ts, plugins/web-ui/src/spend.ts and plugins/web-ui/src/admin/spend.ts
Core hosts the public sign-in front door. Optional embedded auth enables email sign-in; omitting it retains external OIDC sign-in configured in env.core. Web UI README describes the portal as the public SSO front door.
Kind
documented
Locator
Migration configuration; external OIDC sign-in, paired with web-ui README public SSO front door
Projects have one owner and members. Any active member can add internal members and set the icon; only the owner can remove members or rename; other actors get forbidden. Roster changes are audited.
Share creates immutable read-only snapshot of visible messages/replies/attachments. Internal audience needs internal sign-in; public bearer link permits downloads. Intermediate reasoning/tools/raw metadata are excluded. No update/revoke control; access disappears if creator loses original access.
Audit events record actor, action, resource, scope and status for approvals, security flags, credentials, connectors, sharing, sandboxes, sessions and admin changes, read through GET /v1/admin/audit. Every tool call is committed to the session item log.
Kind
source-inspected
Locator
AuditEvent; GET /v1/admin/audit; docs/SPEC.md item log
Files uploads publish durable S3 bytes/metadata separate from sandbox life. Actor/conversation-bound multipart transfer resumes from durable state, has 100 GiB file/four active-upload limits and 24-hour expiry. Deletion records tombstones. Published artifact remains after sandbox retirement.
Agents publish apps (apps action publish) reachable only by the owner and people it is shared with by scope, teammate or email (view or manage); public links are refused unless an org admin enables external sharing.
LICENSE is MIT (QM contributors). The headless core (src/), deployment CLI (cli/), web UI and Slack plugins (plugins/), desktop/ and ios/ clients sit in the same repository with no separate license file.
qm init creates a deployment directory from the npm package in an operator-owned repository; the agent confirms the operator's own cloud account and billing; sign-in uses the built-in email auth broker or the operator's identity provider. No QM or YC vendor account is part of setup.
Assets include conversation and model request data, memory, files, workspaces and audit records. The operator controls the cloud account, database, object storage, keys and identity provider; model providers receive the prompts and request data sent to them; browser providers receive browser traffic.
Kind
documented
Locator
Assets and actors; Trust boundaries and operator assumptions
Says you run QM in your own cloud with your own models and keys, and the license is MIT. Hosted versions come from third parties (Agent 37, E2B, DigitalOcean), and the README gives no price for them.
v0.1.18 (2026-11-11) is the latest stable release after v0.1.17 (2026-11-10) and v0.1.16 (2026-11-04); v0.1.19 (2026-11-12) and desktop-v0.1.6 (2026-11-06, Apple Silicon) are prereleases. Versions remain pre-1.0.
v0.1.18 (2026-11-11) is marked Latest; v0.1.19 (2026-11-12) is a pre-release. Earlier stable releases are v0.1.17 (2026-11-10) and v0.1.16 (2026-11-04). No release cadence is stated in the releases, README or SECURITY.md.
Kind
documented
Locator
Release list (gh release list), retrieved 2026-11-22
QM is deployed by the organization in its own cloud with its own models and keys; hosted versions are offered by third parties. Crons, watches and inbound webhooks keep working while the user is away. The README states no QM price or paid plan.